端侧模型部署工程师
Tasks
- Collaborate with hardware teams on deployment方案
- Convert and export models for deployment
- Create test cases for deployment validation
- Deploy deep learning models
- Develop and optimize CUDA operators
- Implement model compression quantization pruning
- Monitor inference performance
- Optimize model performance on target hardware
- Package models as inference services
- Research edge computing and embedded deployment scenarios
- Tune models for consistency across hardware
- Write automated deployment scripts
Perks/Benefits
- N/A
Skills/Tech-stack
C plus plus | CUDA | DSP | Embedded Systems | GPU | Heterogeneous computing | Inference Optimization | Inference engine | Knowledge Distillation | Linux | Model Compression | Model Conversion | Model export | NPU | ONNX | ONNX Runtime | OpenVINO | Performance Monitoring | Pruning | PyTorch | Python | Quantization | Scripting | TensorFlow | TensorRT
Education
N/A
Related jobs
-
Ai算法实习生（振动与力学方向） CNY 25K-37KAPI Integration | Convolutional Neural Network | Keras | Langchain | Neural NetworkEntry-level Internship深圳9h ago
-
Associate Director, Data and Analytics Specialist CNY 240K-360KAgile | Ansible | Apache Spark | Bamboo | BitbucketMid-level Full TimeXi'an, Shaanxi, China18h ago
-
Analyst, Data Science CNY 144K-240KApplication Integration | Debugging | Documentation | Java | JavaScriptSenior-level Full TimeCN-M Plaza, China1d ago
-
Senior Perception Engineer CNY 360K-600KAlgorithm Optimization | C++ | Computer Vision | Embedded Systems | Multi SensorDevelopment opportunities | Supportive work environmentSenior-level Full Time5-8F TOWER C, 788 JINZHONG ROAD, …1d ago
-
Principal Perception Engineer CNY 360K-600KC++ | Knowledge Distillation | Model Conversion | Model Pruning | Network CompressionSenior-level Full Time5-8F TOWER C, 788 JINZHONG ROAD, …1d ago
-
Senior Specialist, AI Application CNY 360K-600KAgile | Angular | Cloud Platforms | Generative AI | JavaSenior-level Full TimeCN-OCG International Center, Cheng Du, China1d ago
-
Senior-level Full TimeCN-OCG International Center, Cheng Du, China1d ago
-
Principal Specialist, AI Application CNY 240K-480KAgentic Workflows | Async Programming | Authentication | Authorization | Distributed SystemsSenior-level Full TimeCN-M Plaza, China1d ago
-
Principal Specialist, AI Application CNY 240K-480KAgentic Workflows | Asynchronous programming | Cloud Computing | Distributed Systems | DockerSenior-level Full TimeCN-M Plaza, China1d ago
-
Embedded Software Engineer CNY 150K-240KC# | C++ | Code review | Computer Networking | Configuration ManagementEmployee assistance programs | Flexible spending accounts | Health savings account | Healthy Lifestyle Programs | Life insuranceMid-level Full TimeWuxi, Jiangsu, China1d ago
-
Entry-level Internship北京、上海1d ago
-
Behavior Cloning | C++ | Cloud processing | Control | DaggerEntry-level Internship北京、上海 R1d ago
-
Entry-level Full Time上海、深圳 R1d ago
-
Entry-level Internship上海、深圳 R1d ago
-
Entry-level Internship上海1d ago
-
真机强化学习实习生 CNY 25K-37KActor-critic | Deep Q Networks | Embodied Foundation Model | Foundation Model | Isaac-GymEntry-level Internship上海1d ago
-
Entry-level Internship上海1d ago
-
Entry-level Internship上海1d ago
-
具身多模态数据分析算法开发实习生 CNY 25K-37KASR | Anomaly Detection | Automatic Speech Recognition | Cloud processing | Computer VisionInternship experience | MentorshipEntry-level Internship上海1d ago
-
Mid-level Full Time广州1d ago
-
Mid-level Full Time深圳、上海、北京、中国香港1d ago
-
Mid-level Full Time深圳、上海、北京、中国香港1d ago
-
Mid-level Full Time深圳、上海、北京、中国香港1d ago
-
Entry-level Full Time深圳、北京、上海1d ago
-
Entry-level Full Time深圳、上海1d ago